4

我用 pytorch 编码，我想用resnet-18作为 Faster R-RCNN 的主干。当我打印resnet18的结构时，这是输出：

>>import torch
>>import torchvision
>>import numpy as np
>>import torchvision.models as models

>>resnet18 = models.resnet18(pretrained=False)
>>print(resnet18)


ResNet(
  (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
  (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (relu): ReLU(inplace=True)
  (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
  (layer1): Sequential(
    (0): BasicBlock(
      (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace=True)
      (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (1): BasicBlock(
      (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace=True)
      (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
  )
  (layer2): Sequential(
    (0): BasicBlock(
      (conv1): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace=True)
      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (downsample): Sequential(
        (0): Conv2d(64, 128, kernel_size=(1, 1), stride=(2, 2), bias=False)
        (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (1): BasicBlock(
      (conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace=True)
      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
  )
  (layer3): Sequential(
    (0): BasicBlock(
      (conv1): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace=True)
      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (downsample): Sequential(
        (0): Conv2d(128, 256, kernel_size=(1, 1), stride=(2, 2), bias=False)
        (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (1): BasicBlock(
      (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace=True)
      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
  )
  (layer4): Sequential(
    (0): BasicBlock(
      (conv1): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace=True)
      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (downsample): Sequential(
        (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
        (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (1): BasicBlock(
      (conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace=True)
      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
  )
  (avgpool): AdaptiveAvgPool2d(output_size=(1, 1))
  (fc): Linear(in_features=512, out_features=1000, bias=True)
)

我的问题是，直到哪一层是特征提取器？AdaptiveAvgPool2d应该是 Faster R-CNN 主干的一部分吗？

在这个教程中，展示了如何用任意主干训练 Mask R-CNN，我想用 Faster R-CNN 做同样的事情，并用 resnet-18 训练 Faster R-CNN，但直到哪一层应该是一部分特征提取器让我感到困惑。

我知道如何使用 resnet+Feature Pyramid Network 作为主干，我的问题是关于 resent。

4

3 回答 3

8

如果我们想使用自适应平均池的输出，我们将这段代码用于不同的 Resnet：

# backbone
        if backbone_name == 'resnet_18':
            resnet_net = torchvision.models.resnet18(pretrained=True)
            modules = list(resnet_net.children())[:-1]
            backbone = nn.Sequential(*modules)
            backbone.out_channels = 512
        elif backbone_name == 'resnet_34':
            resnet_net = torchvision.models.resnet34(pretrained=True)
            modules = list(resnet_net.children())[:-1]
            backbone = nn.Sequential(*modules)
            backbone.out_channels = 512
        elif backbone_name == 'resnet_50':
            resnet_net = torchvision.models.resnet50(pretrained=True)
            modules = list(resnet_net.children())[:-1]
            backbone = nn.Sequential(*modules)
            backbone.out_channels = 2048
        elif backbone_name == 'resnet_101':
            resnet_net = torchvision.models.resnet101(pretrained=True)
            modules = list(resnet_net.children())[:-1]
            backbone = nn.Sequential(*modules)
            backbone.out_channels = 2048
        elif backbone_name == 'resnet_152':
            resnet_net = torchvision.models.resnet152(pretrained=True)
            modules = list(resnet_net.children())[:-1]
            backbone = nn.Sequential(*modules)
            backbone.out_channels = 2048
        elif backbone_name == 'resnet_50_modified_stride_1':
            resnet_net = resnet50(pretrained=True)
            modules = list(resnet_net.children())[:-1]
            backbone = nn.Sequential(*modules)
            backbone.out_channels = 2048
        elif backbone_name == 'resnext101_32x8d':
            resnet_net = torchvision.models.resnext101_32x8d(pretrained=True)
            modules = list(resnet_net.children())[:-1]
            backbone = nn.Sequential(*modules)
            backbone.out_channels = 2048

如果我们想使用卷积特征图，我们使用以下代码：

 # backbone
        if backbone_name == 'resnet_18':
            resnet_net = torchvision.models.resnet18(pretrained=True)
            modules = list(resnet_net.children())[:-2]
            backbone = nn.Sequential(*modules)

        elif backbone_name == 'resnet_34':
            resnet_net = torchvision.models.resnet34(pretrained=True)
            modules = list(resnet_net.children())[:-2]
            backbone = nn.Sequential(*modules)

        elif backbone_name == 'resnet_50':
            resnet_net = torchvision.models.resnet50(pretrained=True)
            modules = list(resnet_net.children())[:-2]
            backbone = nn.Sequential(*modules)

        elif backbone_name == 'resnet_101':
            resnet_net = torchvision.models.resnet101(pretrained=True)
            modules = list(resnet_net.children())[:-2]
            backbone = nn.Sequential(*modules)

        elif backbone_name == 'resnet_152':
            resnet_net = torchvision.models.resnet152(pretrained=True)
            modules = list(resnet_net.children())[:-2]
            backbone = nn.Sequential(*modules)

        elif backbone_name == 'resnet_50_modified_stride_1':
            resnet_net = resnet50(pretrained=True)
            modules = list(resnet_net.children())[:-2]
            backbone = nn.Sequential(*modules)

        elif backbone_name == 'resnext101_32x8d':
            resnet_net = torchvision.models.resnext101_32x8d(pretrained=True)
            modules = list(resnet_net.children())[:-2]
            backbone = nn.Sequential(*modules)
于 2020-01-09T06:51:26.780 回答
3

torchvision 自动接受 vgg 和 mobilenet 的特征提取层。.features自动从主干模型中提取所需的相关层，并将其传递到对象检测管道。您可以在resnet_fpn_backbone函数中阅读更多相关信息。

在您分享的对象检测链接中，您只需更改backbone = torchvision.models.mobilenet_v2(pretrained=True).features为backbone = resnet_fpn_backbone('resnet50', pretrained_backbone).

只是为了让您简要了解一下，resnet_fpn_backbone函数利用您提供的 resnet 主干名称 (18, 34, 50 ...)，实例化视网膜网络并使用forward提取第 1 层到第 4 层。这个带有 FPN 的主干将在更快的 RCNN中用作主干。

于 2019-10-13T11:57:57.703 回答
1

我在新版本的 torch 和 torchvision 中使用了类似的东西。

def get_resnet18_backbone_model(num_classes, pretrained):
    from torchvision.models.detection.backbone_utils import resnet_fpn_backbone

    print('Using fasterrcnn with res18 backbone...')

    backbone = resnet_fpn_backbone('resnet18', pretrained=pretrained, trainable_layers=5)

    anchor_generator = AnchorGenerator(
        sizes=((16,), (32,), (64,), (128,), (256,)),
        aspect_ratios=tuple([(0.25, 0.5, 1.0, 2.0) for _ in range(5)]))

    roi_pooler = torchvision.ops.MultiScaleRoIAlign(featmap_names=['0', '1', '2', '3'],
                                                    output_size=7, sampling_ratio=2)

    # put the pieces together inside a FasterRCNN model
    model = FasterRCNN(backbone, num_classes=num_classes,
                       rpn_anchor_generator=anchor_generator,
                       box_roi_pool=roi_pooler)
    return model

请注意， resnet_fpn_backbone() 已经将backbone.out_channels 设置为正确的值。

于 2020-09-07T10:08:30.297 回答